Papers › Causal Explanation of Convolutional Neural Networks

Causal Explanation of Convolutional Neural Networks

13 Sep 2021ECML 2021 9archive 2025-07-28

Hichem Debbi

In this paper we introduce an explanation technique for Convolutional Neural Networks (CNNs) based on the theory of causality by Halpern and Pearl [12]. The causal explanation technique (CexCNN) is based on measuring the filter importance to a CNN decision, which is measured through counterfactual reasoning. In addition, we employ extended definitions of causality, which are responsibility and blame to weight the importance of such filters and project their contribution on input images. Since CNNs form a hierarchical structure, and since causal models can be hierarchically abstracted, we employ this similarity to perform the most important contribution of this paper, which is localizing the important features in the input image that contributed the most to a CNN’s decision. In addition to its ability in localization, we will show that CexCNN can be useful as well for model compression through pruning the less important filters. We tested CexCNN on several CNNs architectures and datasets. (The code is available on https://github.com/HichemDebbi/CexCNN)

PaperPDFCode

Code

HichemDebbi/CexCNN mentioned in paper report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Counterfactual ExplanationCounterfactual ReasoningModel CompressionNetwork PruningWeakly-Supervised Object Localization

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Weakly-Supervised Object Localization ImageNet CexCNN GT-known localization accuracy 67.65 #3 of 6 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Pruning

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections